inworld-tts-2) is our most capable model and the recommended choice here, with more accurate pronunciation and intonation and more natural-sounding speech.
Supported languages
Realtime TTS-2 (inworld-tts-2) supports 200+ unique languages and locales (BCP-47 codes) — from broad languages like es (Spanish) to regional locales like es-MX (Mexican Spanish). The languages we actively support and test are listed below.
Generally available languages
These languages are generally available (GA), offering the highest quality and the most natural pronunciation:| Language | Code | Timestamps | Normalization |
|---|---|---|---|
| Arabic | ar | Yes | No |
| Chinese | zh | Yes | Yes |
| Dutch | nl | Yes | Yes |
| English | en | Yes | Yes |
| French | fr | Yes | Yes |
| German | de | Yes | Yes |
| Hebrew | he | Yes | No |
| Hindi | hi | Yes | Yes |
| Italian | it | Yes | Yes |
| Japanese | ja | Yes | Yes |
| Korean | ko | Yes | No |
| Polish | pl | Yes | Yes |
| Portuguese | pt | Yes | Yes |
| Russian | ru | Yes | No |
| Spanish | es | Yes | Yes |
Experimental languages
These languages are supported byinworld-tts-2 only. To try one, design or clone a voice in that language.
Show all experimental languages (alphabetical)
Show all experimental languages (alphabetical)
| Language | Code * | Timestamps | Normalization |
|---|---|---|---|
| Afrikaans | af | No | No |
| Albanian | sq | No | No |
| Amharic | am | No | No |
| Armenian | hy | No | No |
| Assamese | as | Yes | No |
| Azerbaijani | az | No | No |
| Basque | eu | No | No |
| Belarusian | be | No | No |
| Bengali | bn | Yes | No |
| Bulgarian | bg | No | No |
| Burmese | my | No | No |
| Cantonese | yue | No | No |
| Catalan | ca | No | No |
| Cebuano | ceb | No | No |
| Croatian | hr | No | No |
| Czech | cs | No | No |
| Danish | da | Yes | No |
| Eastern Yiddish | yih | No | No |
| Egyptian Arabic | arz | Yes | No |
| Estonian | et | No | No |
| Filipino | fil | No | No |
| Finnish | fi | No | No |
| Galician | gl | No | No |
| Garhwali | gbm | No | No |
| Georgian | ka | No | No |
| Greek | el | Yes | No |
| Gujarati | gu | Yes | No |
| Gulf Arabic | afb | Yes | No |
| Haitian Creole | ht | No | No |
| Hijazi Arabic | acw | Yes | No |
| Hungarian | hu | No | No |
| Icelandic | is | No | No |
| Indonesian | id | Yes | No |
| Javanese | jv | No | No |
| Kannada | kn | Yes | No |
| Kazakh | kk | No | No |
| Konkani | kok | No | No |
| Lao | lo | No | No |
| Latvian | lv | No | No |
| Libyan Arabic | ayl | Yes | No |
| Lithuanian | lt | No | No |
| Luxembourgish | lb | No | No |
| Macedonian | mk | No | No |
| Maithili | mai | No | No |
| Malagasy | mg | No | No |
| Malay | ms | No | No |
| Malayalam | ml | Yes | No |
| Marathi | mr | Yes | No |
| Mongolian | mn | No | No |
| Najdi Arabic | ars | Yes | No |
| Nepali | ne | Yes | No |
| Northern Uzbek | uzn | No | No |
| Norwegian Bokmål | nb | No | No |
| Norwegian Nynorsk | nn | No | No |
| Odia | or | Yes | No |
| Omani Arabic | acx | No | No |
| Pashto | ps | No | No |
| Persian | fa | Yes | No |
| Piedmontese | pms | No | No |
| Punjabi | pa | Yes | No |
| Romanian | ro | No | No |
| Serbian | sr | No | No |
| Sindhi | sd | No | No |
| Sinhala | si | No | No |
| Slovak | sk | No | No |
| Slovenian | sl | No | No |
| Swahili | sw | No | No |
| Swedish | sv | Yes | No |
| Tamil | ta | Yes | No |
| Telugu | te | Yes | No |
| Thai | th | Yes | No |
| Tunisian Arabic | aeb | Yes | No |
| Turkish | tr | Yes | Yes |
| Ukrainian | uk | Yes | No |
| Urdu | ur | Yes | No |
| Uzbek | uz | No | No |
| Vietnamese | vi | Yes | No |
| Võro | vro | No | No |
| Welsh | cy | No | No |
Accents and regional variants: A voice reproduces the specific accent it was cloned in (e.g., a voice cloned in British English speaks
en-GB natively). If your voice wasn’t cloned in the accent you need, pass the matching BCP-47 regional code in the language field (e.g., en-GB, es-MX, pt-BR) to steer it. See Specifying a language below.Text normalization is language-specific, not locale-specific — English is normalized the same way whether you target
en-US or en-GB, even though conventions for dates, currencies, and the like can differ. If you need locale-specific formatting, normalize that text yourself.TTS-1.5:
inworld-tts-1.5-max and inworld-tts-1.5-mini support 15 languages: Arabic, Chinese, Dutch, English, French, German, Hebrew, Hindi, Italian, Japanese, Korean, Polish, Portuguese, Russian, and Spanish. For new multilingual projects, we recommend Realtime TTS-2.Cross-lingual support
Realtime TTS-2 supports cross-lingual synthesis, where the same voice can be used across multiple languages. Depending on the voice and language, the voice may retain the accent of the original voice language when speaking a different language (e.g., a French voice may speak English with a French accent). TTS-1.5 performs optimally when synthesizing text in the same language as the voice prompt. You’ll achieve the best quality, pronunciation, and naturalness by matching the voice’s prompt language to your text content. For the most natural, consistent cross-lingual results, we recommend specifying the language to synthesize in and localizing the voice.Specifying a language
Use thelanguage field to tell the model which language (as specified by a BCP-47 language tag) the voice should speak the text in. When set, the service will:
- Apply text normalization (if enabled) for the target language (e.g., speaking numbers in the target language).
- Use the voice’s localized prompt for that language, if one exists. If no localized prompt is available, the model will be steered to speak in the target language.
language is omitted, the original voice prompt is used and the language for normalization (if enabled) is auto-detected from the input text.
If you are sending short requests with only numbers or dates (e.g., 123-456-7890), auto-detection may not have enough context to detect the right language. In those cases, we recommend specifying a language for most consistent results.
Voice localization
Voice localization adapts a voice to a target language so it sounds like a native speaker of that language — delivering fluent, natural speech without carrying over the accent of the voice’s original language. (By contrast, specifying a language on an un-localized voice may retain the original accent.) It is supported for all Inworld TTS models.Open the Voices page in Portal
In Inworld Portal, go to Voices and select the My voices tab. Hover over an English voice to open its details panel on the right.
Voice localization is currently only supported for voices where the original audio was in English. Support for additional languages is coming soon.
Choose a target language
Pick a target language from the dropdown and click Localize, which will start generating localized prompt candidates. This may take up to 2 minutes.
Review candidates
After generation, you’ll see a few localized prompt candidates. Listen to each and pick the one that sounds most natural and native, then click Save.If none sound right, you can click Regenerate. You may want to change the script before regenerating, since the script influences the generated voice.
Next steps
Voice Cloning
Clone a voice once and reuse it across languages.
Custom Pronunciation
Use IPA notation to control pronunciation of proper nouns and edge cases.